Flowsery

Get Visitors by Device

get_devices

Read-only

Get device type breakdown — desktop vs mobile vs tablet split.

Input Schema

TableJSON Schema

Name	Required	Description
`endAt`	No	ISO 8601 end date (e.g. "2026-01-31")
`limit`	No	Max results (1-1000, default: 100)
`domain`	No	Website domain to query. Required when using a workspace token unless websiteId is provided.
`offset`	No	Pagination offset (default: 0)
`startAt`	No	ISO 8601 start date (e.g. "2026-01-01")
`timezone`	No	IANA timezone (e.g. "America/New_York"). Falls back to site default.
`filter_os`	No	Filter by operating system
`websiteId`	No	Website ID to query. Required when using a workspace token unless domain is provided.
`filter_ref`	No	Filter by ref URL parameter
`filter_via`	No	Filter by via URL parameter
`filter_city`	No	Filter by city
`filter_goal`	No	Filter by goal name
`filter_page`	No	Filter by page path
`filter_device`	No	Filter by device type: desktop, mobile, tablet
`filter_region`	No	Filter by region
`filter_source`	No	Filter by source URL parameter
`filter_browser`	No	Filter by browser name
`filter_channel`	No	Filter by marketing channel
`filter_country`	No	Filter by country
`filter_hostname`	No	Filter by hostname
`filter_referrer`	No	Filter by referrer domain
`filter_utm_term`	No	Filter by UTM term
`filter_entry_page`	No	Filter by entry/landing page
`filter_utm_medium`	No	Filter by UTM medium
`filter_utm_source`	No	Filter by UTM source
`filter_utm_content`	No	Filter by UTM content
`filter_utm_campaign`	No	Filter by UTM campaign

Output Schema

TableJSON Schema

Name	Required	Description	Default
`result`	No	Device types (desktop, mobile, tablet) with visitor counts.

Schema Changelog

Changes observed during successful MCP inspections. Dates show when Glama detected each change.

First observedSep 1, 2026

TDQS

A3.5/5.0

Behavior3/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already mark it read-only and non-destructive, so the safety profile is covered. The description adds that the result is an aggregated split by device category, which is useful, but it does not add further behavioral context such as how filters or pagination affect the breakdown.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single front-loaded sentence with no filler; the em-dash efficiently specifies the grouping. Every element earns its place.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With 27 parameters, many sibling tools, and no usage guidance, the description is minimal but the output schema and full parameter descriptions fill most operational gaps. It is adequate for a simple read-only breakdown tool, though it leaves selection guidance to inference.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the parameters are fully documented there. The description adds little beyond the filter_device domain values, but because the schema already carries the meaning, baseline 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb ('Get') and resource ('device type breakdown') and names the exact grouping dimensions (desktop vs mobile vs tablet), which distinguishes it from sibling analytics tools like get_browsers or get_operating_systems.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance on when to choose this over siblings such as get_breakdown, get_overview, or other get_* tools. The description implies a use case but provides no exclusions or alternative routing.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

All Flowsery tools Inspect

Try in Browser

RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

A3.6/5.0

Disambiguation5/5

Each tool serves a distinct purpose: get_* tools cover different analytics dimensions (browsers, cities, countries, etc.) with clear scopes, while issue management and tracking tools are clearly separated. Even get_breakdown is explicitly scoped to dimensions without dedicated endpoints, avoiding overlap.

Naming Consistency5/5

All tools follow a consistent verb_noun pattern with snake_case (delete_goals, get_overview, track_goal, update_issue_status). Verbs are specific and predictable (get, delete, track, list, update), and there are no naming style mixes.

Tool Count2/5

At 27 tools, the set exceeds the 25-tool threshold considered 'too many.' While the domain is broad (analytics, tracking, issues), many get_* tools could be consolidated into get_breakdown with filter parameters, making the count feel inflated rather than necessarily well-scoped.

Completeness4/5

The tool surface covers the full analytics lifecycle: overview, time series, breakdowns, real-time data, visitor profiles, goal/payment tracking and deletion, plus AI issue listing/detail/status updates. Minor gaps exist (e.g., no update for goals/payments, no explicit list of defined goals), but these are non-critical and don't impair typical workflows.

Resources

Need Help?